© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102356
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsOptional
    -0.97
    ͐
    -0.93
    捞
    -0.92
    CHECKBOX
    -0.88
     Bonds
    -0.88
    omości
    -0.85
     ел
    -0.85
    מר
    -0.85
     творчество
    -0.84
    demann
    -0.82
    POSITIVE LOGITS
     pertenecen
    1.02
    じた
    0.94
    谒
    0.88
     afectan
    0.87
    ťaž
    0.84
     octane
    0.84
     appropriate
    0.83
     Gött
    0.82
     uſe
    0.82
     necesitar
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.